© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34066
    Prev
    Next
    INDEX
    Explanations

    contract formation and acceptance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cust
    -0.10
     Humph
    -0.10
     Needle
    -0.10
     contractual
    -0.10
     Cust
    -0.10
    cust
    -0.09
     Babe
    -0.09
    indo
    -0.09
     cus
    -0.09
    arez
    -0.09
    POSITIVE LOGITS
     performance
    0.16
    performance
    0.13
     oral
    0.13
     execut
    0.12
    Performance
    0.12
     Performance
    0.12
     uncon
    0.12
    å±¥
    0.12
     enforce
    0.11
     enforcement
    0.11
    Activations Density 0.039%

    No Known Activations